Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

2026-07-03

AI Summary

This work addresses the challenge of human-AI misalignment in collaborative decision-making, where humans often exhibit either overreliance on or insufficient trust in AI systems. To mitigate this issue, the authors propose a human-centered, reflective human-AI collaboration framework that uniquely integrates human calibration modeling with reinforcement learning from language feedback. The collaborative process is formalized as a stochastic game, enabling iterative refinement of AI behavior through natural language feedback to align preferences and optimize decision strategies. Experimental results demonstrate that this approach significantly enhances decision effectiveness and yields high-quality recommendations that better conform to human expectations.

Abstract

The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback. Concurrently, it seeks to align decisions with human expectations, preferences, and needs while mitigating risks associated with AI non-determinism. However, humans frequently over- or under-rely on AI recommendations, and current AI systems remain poorly calibrated to human expectations. To address these challenges, we introduce a human-AI collaborative decision-making framework designed to augment human capabilities and align AI agents with human preferences and expectations. Specifically, this paper (a) formulates the collaborative decision-making task as a stochastic game between an AI agent and a human player, and (b) proposes the Human-Centric Reflective Architecture (HCRA), which integrates human-calibrated models with reinforcement learning agents that leverage linguistic feedback in an iterative, reflective process. Evaluation results demonstrate that HCRA enhances decision-making effectiveness and delivers high-quality recommendations.

Problem

• human-AI collaboration
• decision-making
• human reliance
• AI alignment
• expectation calibration

Innovation

• Human-AI collaboration
• Reflective architecture
• Stochastic game
• Human-calibrated models
• Linguistic feedback